# Agent Planners

> Agent Planners is a human-approved, multi-agent harness for marketing automation across Google Ads, Google Analytics 4, BigQuery and Search Console. An orchestrator plans the work, specialist agents execute it across every account, and every change that writes pauses at an approval gate (in-app or email magic-link). It supports 24/7 cron schedules, per-account memory, reusable skills, organizations with roles, per-agent model choice via a built-in AI Gateway, and custom tools over MCP.

## Documentation
- [Getting started](https://www.agentplanners.com/docs/getting-started): Connect an ad account, write a goal in plain language, and approve what the agent ships. The five-minute path from sign-up to your first optimization.
- [Agent best practices: getting the most out of the system](https://www.agentplanners.com/docs/best-practices): How to get reliable, safe, cost-effective results from an AI agent for ad ops — writing goals, guardrails, approvals, model choice, skills, schedules and true ROAS.
- [Agent playbooks](https://www.agentplanners.com/docs/playbooks): Concrete, multi-step jobs the agent runs end-to-end — audits, budget rebalancing, search-term mining, remarketing, PMax, and cross-account cleanups. Copy a goal and go.
- [Credits & billing](https://www.agentplanners.com/docs/credits): How credits work, what consumes them, the free monthly allotment, top-up packs, where to see your usage, and how to lower your credit burn.
- [Add your own MCP server](https://www.agentplanners.com/docs/mcp): Connect your own tools to the agent over the Model Context Protocol (MCP), plus thousands of SaaS actions via Composio. Fields, steps, and how tools are discovered.
- [Connect & use Composio](https://www.agentplanners.com/docs/composio): Give the agent 250+ SaaS app integrations — Slack, Gmail, Google Sheets, HubSpot, Salesforce, Notion and more — with one Composio API key. How to connect apps and have the agent act across them, with every write approved by you.
- [Agents & models](https://www.agentplanners.com/docs/agents): The orchestrator plus six specialist agents, and how to choose the model for each one through the built-in AI Gateway — GPT, Claude, Gemini, Qwen, DeepSeek and more.
- [Bring your own model (BYOM)](https://www.agentplanners.com/docs/byom): Point every agent at your own OpenAI-compatible endpoint — Azure AI, vLLM, OpenRouter or any self-hosted model. LLM tokens on your endpoint aren't billed as platform credits; you pay your provider directly.
- [Connect your platforms](https://www.agentplanners.com/docs/integrations): Natively connect Google Ads, DV360, Campaign Manager 360, Meta Ads, TikTok Ads, Google Ad Manager, AdSense, AdMob, GA4, Search Console, BigQuery and Shopify — plus 250+ more apps (Gmail, Outlook, Slack, Notion, HubSpot…) via Composio and your own tools via custom MCP. Pick accounts with the context picker and run one task across an entire MCC.
- [Approvals & workflow](https://www.agentplanners.com/docs/approvals): Plan → approve → execute. How every write pauses at an approval gate, in-app or by email magic-link, with pre-approval, auto-approve, stale-state checks and the audit log.
- [Schedules](https://www.agentplanners.com/docs/schedules): Turn any goal into a recurring job on a cron — hourly, daily or weekly — in your timezone, re-evaluating against live data on every fire, with optional email approvals.
- [Skills, memory & teams](https://www.agentplanners.com/docs/skills-memory): Capture your methodology as Skills, keep per-account memory (targets, protected campaigns, rules), and run isolated organizations with admin/editor/member roles.
- [Shopify: generate an Admin token and let the agent make changes](https://www.agentplanners.com/docs/shopify): Connect a Shopify store in three tiers — domain-only storefront, read-only Admin data, and approval-gated Admin writes. How to create the Admin API access token, which scopes to grant, and the use cases the agent runs against a store.
- [Generate PPT decks & reports with AI](https://www.agentplanners.com/docs/ppt-and-reports): Turn an analysis or run into a client-ready PowerPoint deck and a written report — drafted by the agent from your real data, then editable and exportable.
- [AI model pricing & credits ranking](https://www.agentplanners.com/docs/model-pricing): Every selectable AI model ranked cheapest to priciest by credit cost class.

## Platforms
- [AI agent for Google Ads: audits, optimization and campaign builds](https://www.agentplanners.com/platforms/google-ads): Connect Google Ads (including MCC) and let an AI agent audit performance, mine negatives, rebalance budgets and build campaigns — every write pauses for your approval.
- [AI agent for DV360 (Display & Video 360): programmatic campaign management](https://www.agentplanners.com/platforms/dv360): Automate Display & Video 360 — insertion orders, line items, deals, audiences and Bid Manager reporting — with native reach forecasting and human approval on every write.
- [AI agent for GA4: cross-channel analytics without spreadsheets](https://www.agentplanners.com/platforms/ga4): Connect Google Analytics 4 and let an AI agent build funnel and channel reports on demand, mark key events, and turn traffic data into remarketing audiences for Google Ads.
- [AI agent for Search Console: SEO monitoring without spreadsheets](https://www.agentplanners.com/platforms/search-console): Connect Search Console and let an AI agent track rankings, surface content gaps, and cross-reference organic performance with your paid spend — read-only, nothing to configure.
- [AI agent for BigQuery: true ROAS and first-party analysis](https://www.agentplanners.com/platforms/bigquery): Connect BigQuery and let an AI agent write and run SQL against your own data warehouse — joining ad spend with real revenue for true, profit-aware ROAS. Read-only.
- [AI agent for Google Ad Manager: publisher revenue analysis](https://www.agentplanners.com/platforms/google-ad-manager): Connect Google Ad Manager and let an AI agent build ad-hoc revenue, fill-rate and eCPM reports, flag underperforming inventory, and cross-reference publisher revenue with ad spend.
- [AI agent for AdSense: site monetization analysis](https://www.agentplanners.com/platforms/adsense): Connect Google AdSense and let an AI agent track earnings, RPM and CTR by ad unit and page, flag revenue drops, and correlate content traffic with ad revenue. Read-only.
- [AI agent for AdMob: app monetization and mediation-waterfall optimization](https://www.agentplanners.com/platforms/admob): Connect AdMob and let an AI agent track earnings, eCPM and mediation performance by app, ad format and country — ranking ad sources by observed eCPM and fill rate to find waterfall wins. Read-only.
- [AI agent for Campaign Manager 360: ad-server reporting and entity audits](https://www.agentplanners.com/platforms/cm360): Connect Campaign Manager 360 and let an AI agent run ad-server reports, audit campaigns, placements, creatives and Floodlight configuration, and reconcile CM360 delivery with your buying platforms. Trafficking writes stay human-approved.

## Resources (guides)
- [AI agents for Google Ads: how they work (and where humans stay in control)](https://www.agentplanners.com/resources/ai-agents-for-google-ads): AI agents can read, reason about, and act on your Google Ads account. Here's how they work, what they automate, and why human approval still matters.
- [Google Ads automation: rules vs scripts vs AI agents](https://www.agentplanners.com/resources/google-ads-automation): A practical guide to Google Ads automation: when to use automated rules, scripts, or AI agents — and exactly what's safe to automate vs keep manual.
- [True ROAS: joining Google Ads with BigQuery and first-party data](https://www.agentplanners.com/resources/true-roas-bigquery): Platform ROAS can mislead. Learn how to join Google Ads with BigQuery and your own revenue data in SQL to measure true, profit-aware return on ad spend.
- [What is MCP (Model Context Protocol)? A plain-English guide for marketers](https://www.agentplanners.com/resources/what-is-mcp): MCP is the open standard that lets AI agents safely connect to your tools and data. Here's what it is, how it works, and why it matters for ad ops.
- [Human-in-the-loop AI for advertising: why approval gates matter](https://www.agentplanners.com/resources/human-in-the-loop-ai-advertising): As AI takes on ad ops, human-in-the-loop keeps you in control. Learn how approval gates, spend caps and audit logs reduce risk — and what regulators expect.
- [Managing multiple Google Ads accounts (MCC) with AI](https://www.agentplanners.com/resources/mcc-management-with-ai): Running many Google Ads accounts from one manager account? Learn how AI helps agencies scale audits and optimizations across accounts — with guardrails.
- [Ad-ops & AI glossary: ROAS, CPA, MCC, PMax, GAQL, MCP and more](https://www.agentplanners.com/resources/glossary): Plain-English definitions of the ad-operations and AI terms used across Agent Planners — ROAS, CPA, MCC, RSA, PMax, GAQL, MCP, approval gate and more.

## Comparisons
- [Agent Planners vs Optmyzr](https://www.agentplanners.com/compare/optmyzr): Optmyzr is a mature PPC rule-engine you operate; Agent Planners is an AI agent that does the work and waits for your approval. An honest, side-by-side comparison.
- [Agent Planners vs Madgicx](https://www.agentplanners.com/compare/madgicx): Madgicx is a Meta-ads AI super-app with deep creative analytics; Agent Planners is a multi-platform agent — including Meta — with mandatory human approval on every write. A fair side-by-side.
- [Agent Planners vs Revealbot](https://www.agentplanners.com/compare/revealbot): Revealbot (rebranding to Birch) automates ads with rules you author; Agent Planners is an AI agent that plans the work and pauses writes for approval.
- [Agent Planners vs Opteo](https://www.agentplanners.com/compare/opteo): Opteo is a clean Google-Ads-only recommendation tool; Agent Planners is a multi-platform agent that executes and gates every write behind approval.
- [Agent Planners vs Ryze](https://www.agentplanners.com/compare/ryze): Ryze is a broad multi-channel AI ad manager with optional approval; Agent Planners connects just as many ad platforms plus GA4, BigQuery and Shopify, with approval enforced on every write.
- [Agent Planners vs Smartly.io](https://www.agentplanners.com/compare/smartly-io): Smartly.io is an enterprise social/creative ad platform with custom pricing; Agent Planners is a self-serve, multi-platform agent (including Meta) with a free tier.
- [Agent Planners vs Adalysis](https://www.agentplanners.com/compare/adalysis): Adalysis is a deep PPC auditing + rules tool for Google & Microsoft Ads; Agent Planners is an AI agent that does the work and gates every write behind approval.
- [Agent Planners vs Albert.ai](https://www.agentplanners.com/compare/albert): Albert.ai is fully autonomous, enterprise cross-channel media buying (now part of Zoomd); Agent Planners is self-serve and gates every write behind human approval.
- [Agent Planners vs WordStream](https://www.agentplanners.com/compare/wordstream): WordStream (by LocaliQ) is SMB PPC software with free grader tools and recommendations; Agent Planners is an AI agent that executes and gates every write behind approval.
- [Agent Planners vs Markifact](https://www.agentplanners.com/compare/markifact): Markifact is a no-code AI marketing automation builder — agents, workflows and an MCP server across 500+ operations. Agent Planners is a multi-agent harness with a built-in AI Gateway and native BigQuery ROAS. An honest, side-by-side comparison.

## Alternatives
- [The best Optmyzr alternative in 2026](https://www.agentplanners.com/alternatives/optmyzr): Looking for an Optmyzr alternative? Agent Planners is an AI agent that plans and executes ad-ops work end-to-end, pauses every write for your approval, and joins your own BigQuery data for true ROAS.
- [The best Madgicx alternative in 2026](https://www.agentplanners.com/alternatives/madgicx): Looking for a Madgicx alternative that goes beyond Meta? Agent Planners is a cross-platform AI agent — Google Ads, Meta, TikTok, DV360, GA4 and BigQuery — with an approval gate on every write.
- [The best Opteo alternative in 2026](https://www.agentplanners.com/alternatives/opteo): Looking for an Opteo alternative that executes, not just recommends? Agent Planners plans and runs the work across Google Ads, GA4 and BigQuery, pausing every write for your approval.
- [The best Revealbot alternative in 2026](https://www.agentplanners.com/alternatives/revealbot): Looking for a Revealbot alternative that reasons instead of just running rules? Agent Planners replaces hand-authored automation rules with agents that plan from a goal and pause every write for approval.
- [The best Smartly.io alternative for self-serve teams in 2026](https://www.agentplanners.com/alternatives/smartly-io): Looking for a Smartly.io alternative without an enterprise contract? Agent Planners is a self-serve AI agent across Meta, TikTok, Google Ads, DV360 and BigQuery — a free tier to start, no custom sales process.
- [The best WordStream alternative in 2026](https://www.agentplanners.com/alternatives/wordstream): Looking for a WordStream alternative that goes beyond an audit grader? Agent Planners is an AI agent that plans and executes ad-ops work end-to-end, with true ROAS from your own BigQuery data.

## Blog
- [The state of AI in PPC in 2026: what actually changed](https://www.agentplanners.com/blog/state-of-ai-in-ppc-2026): Agentic AI, MCP, reviewability and first-party ROAS — the five shifts that actually changed paid search in 2026, and what they mean for your ad ops.
- [Agentic AI vs rule-based automation in advertising](https://www.agentplanners.com/blog/agentic-vs-rule-based-automation): Rules and scripts do exactly what you wrote; agentic AI reasons from a goal. Here's the real difference for advertisers — and when each one wins.
- [Why fully-autonomous ad bots fail — the case for human-in-the-loop](https://www.agentplanners.com/blog/case-for-human-in-the-loop-ads): Hand an AI your ad budget with no gate and it will eventually make an expensive, confident mistake. The case for human-in-the-loop — without killing velocity.
- [Cut Google Ads busywork with AI: a 2026 playbook](https://www.agentplanners.com/blog/cut-google-ads-busywork-with-ai): A practical playbook for using AI to remove the repetitive Google Ads work — audits, negatives, budget pacing, reporting — without losing control of the account.
- [AI ad ops for agencies: scale accounts without losing control](https://www.agentplanners.com/blog/ai-ad-ops-for-agencies): How agencies use AI to run audits and optimizations across many client accounts (MCC) — with per-account guardrails, approvals and a dry-run so nothing goes wrong.
- [Beyond Performance Max: staying in control when Google's AI runs the campaign](https://www.agentplanners.com/blog/beyond-performance-max): Performance Max automates reach but hides its reasoning. Here's how to keep visibility and control — with reviewable AI, first-party ROAS and negative-list discipline.
- [Advertising in the age of AI search (ChatGPT & Perplexity)](https://www.agentplanners.com/blog/advertising-in-ai-search): As buyers ask AI assistants instead of typing keywords, discovery is shifting. What marketers should do now — from GEO to first-party measurement.
- [How AI finds and cuts wasted ad spend](https://www.agentplanners.com/blog/find-and-cut-wasted-ad-spend): Most accounts quietly leak budget on zero-converting search terms, low-ROAS campaigns and dead placements. How an AI agent finds the waste and proposes the cuts — with your approval.
- [How to audit a Google Ads account with AI (2026)](https://www.agentplanners.com/blog/google-ads-account-audit-with-ai): A complete Google Ads audit checklist — structure, search terms, budgets, tracking, disapprovals, wasted spend — and how an AI agent runs it in minutes, read-only.
- [Multi-agent systems for marketing, explained](https://www.agentplanners.com/blog/multi-agent-systems-for-marketing): What a multi-agent system is, why an orchestrator plus specialists beats one big prompt, and where it fits in marketing — from research to optimization to reporting.
- [Choosing an AI model for ad ops: cost vs capability](https://www.agentplanners.com/blog/choosing-ai-model-for-ad-ops): Frontier models are powerful but pricey; cheaper models handle most ad-ops work fine. How to match the model to the task and keep your credit spend low.
- [Always-on ad ops: scheduling AI tasks from weekly reviews to 24/7 monitoring](https://www.agentplanners.com/blog/always-on-ai-ad-ops-scheduling): Turn one-off AI tasks into scheduled jobs — weekly reviews, disapproval monitoring, budget pacing, search-term sweeps — that re-evaluate live data and email you what to approve.
- [Agent Planners now has an API and MCP server — run it from Claude, Codex, or any agent](https://www.agentplanners.com/blog/api-mcp-for-external-agents): Agent Planners now exposes a REST API and an MCP server, so Claude Desktop, Claude Code, Codex, or any agent or script you run can create and monitor tasks against your ad accounts — with the same approval gates and guardrails as the in-app Workspace.
- [Why an MCP connection alone shouldn't manage your Meta ad accounts](https://www.agentplanners.com/blog/meta-mcp-ad-account-governance): An MCP server hands an AI agent your Meta Marketing API — with no approval step, no team roles, no audit log and no spend ceiling. What that actually costs, and what a governance layer adds on top.
- [A daily Shopify optimization loop with AI, Google Ads and Search Console](https://www.agentplanners.com/blog/shopify-daily-optimization-with-ai-agent): Shopify knows what sold, Search Console knows what people searched, Google Ads knows what you paid. Wire all three to one AI agent and run a ten-minute daily loop — with every store change approved by you.
- [Build a marketing data hub in BigQuery and teach the agent your own Skills](https://www.agentplanners.com/blog/bigquery-marketing-data-hub-custom-skills): Land third-party data in BigQuery, model it so an AI agent can reason over it, then capture your analysis method as a reusable Skill so every future run follows it instead of improvising.
- [The best AI agent for Google Ads: how to actually choose one (2026)](https://www.agentplanners.com/blog/best-ai-agent-for-google-ads): Eight criteria that separate a real Google Ads AI agent from a dashboard with a chat box — reviewability, write governance, whose numbers it trusts — plus the red flags and where each category of tool fits.
- [The best AI agent for SEO: what to look for beyond content generation](https://www.agentplanners.com/blog/best-ai-agent-for-seo): Most "AI SEO" tools generate text. The useful ones read your Search Console data, find the gap between what you rank for and what you sell, and keep a human between the idea and the publish button.
- [The best AI agent for Google Analytics (GA4): criteria that matter](https://www.agentplanners.com/blog/best-ai-agent-for-google-analytics): GA4 made reporting harder, not easier. Here's how to judge an AI agent for Google Analytics — whether it queries the API directly, handles GA4's data model honestly, and can join analytics to cost and revenue.
- [The best AI agent for DV360: what programmatic actually needs](https://www.agentplanners.com/blog/best-ai-agent-for-dv360): Most AI ad tools are built for Search and social and don't touch DV360 at all. Here's what a Display & Video 360 agent has to understand — the IO/line-item hierarchy, Bid Manager reporting, and why new line items should start as drafts.
- [The best AI agent for Campaign Manager 360: an ad-server buyer's guide](https://www.agentplanners.com/blog/best-ai-agent-for-campaign-manager-360): CM360 is the ad server, not a buying platform — which changes what an AI agent should do with it. Trafficking, Floodlight, the asynchronous reporting lifecycle, and why writes here need the tightest gate in your stack.
- [The AI Ad Ops Benchmark Report (2026): governance across 10 tools](https://www.agentplanners.com/blog/ai-ad-ops-benchmark-report-2026): We scored 10 AI ad-ops tools — ourselves included — on write governance, first-party revenue joins and native platform reach, using each vendor's own public claims. Only one documents mandatory human approval on every write. Full dataset included.
- [How to implement an AI agent for ad ops: a rollout guide](https://www.agentplanners.com/blog/ai-ad-ops-implementation-guide): A practical, week-by-week plan for rolling out an AI agent on a live ad account — connecting platforms, starting read-only, setting guardrails, turning on approval-gated writes, and scaling to a full account or MCC.
- [Ads Data Hub vs BigQuery: what's the difference, and which do you need?](https://www.agentplanners.com/blog/ads-data-hub-vs-bigquery): Ads Data Hub gives you privacy-safe access to Google's log-level ad-exposure data; BigQuery is a general-purpose warehouse for your own data plus whatever platforms export to it. Most ad-ops teams need BigQuery — here's how to tell.
- [RPA vs AI agents for Google Ads: what's actually different](https://www.agentplanners.com/blog/rpa-vs-ai-agents-google-ads): RPA scripts click through the UI exactly as instructed; AI agents reason about a goal through the API. Here's the real distinction for Google Ads, and why RPA is the riskier choice on a live ad account.
- [Composio vs custom MCP: how to connect your AI agent to other tools](https://www.agentplanners.com/blog/composio-vs-mcp-for-ai-agents): Composio gives an AI agent 250+ pre-built SaaS actions with one API key. A custom MCP server exposes your own tools and data on an endpoint you host. Here's how to decide — and how to connect either one.
- [Claude Fable 5 and Claude Opus 5 are now in Agent Planners](https://www.agentplanners.com/blog/claude-fable-5-opus-5-in-agent-planners): Anthropic's newest models, Claude Fable 5 and Claude Opus 5, are live in Agent Planners' model picker — with real credit pricing, a 1M-token context window, and no waiting for us to add them.
- [GPT-5.6 Luna is now the default model — and we caught a pricing bug before it shipped](https://www.agentplanners.com/blog/gpt-5-6-luna-default-model): New Agent Planners organizations now default to GPT-5.6 Luna on every quality-critical agent — 13x cheaper than the model it replaces, on a bigger context window. Here's the pricing story, including the billing bug we found and fixed the same day.
- [How to choose an AI model for each agent: a decision framework](https://www.agentplanners.com/blog/how-to-choose-an-ai-model-for-each-agent): Six agents, 40+ selectable models, one AI Gateway. A concrete framework for which model tier to run on the orchestrator versus a specialist — with real current pricing for GPT-5.6 Luna, Claude Fable 5, Claude Opus 5 and more.
- [The best AI agent for Meta Ads (Facebook & Instagram) in 2026](https://www.agentplanners.com/blog/best-ai-agent-for-meta-ads): Most AI ad tools built for Meta are creative-analytics specialists or rule engines. Here's what to look for in an AI agent that reads, reasons about and executes changes across your Facebook and Instagram campaigns.
- [The best AI agent for TikTok Ads in 2026](https://www.agentplanners.com/blog/best-ai-agent-for-tiktok-ads): TikTok's campaign → ad group → ad hierarchy and creative-first culture need different judgment than Search or Meta. What to look for in an AI agent for TikTok Ads, and where Agent Planners fits.
- [What is GEO (Generative Engine Optimization)? A practical guide](https://www.agentplanners.com/blog/what-is-geo-generative-engine-optimization): SEO gets you ranked; GEO gets you cited. The concrete, checkable techniques — structured data, llms.txt, answer-first writing, freshness — for showing up in ChatGPT, Perplexity and AI Overviews.
- [What is llms.txt? A practical guide (with a working example)](https://www.agentplanners.com/blog/what-is-llms-txt): llms.txt is a plain-text file that gives AI systems a concise index of your site. What it actually is, what to put in it, and a real, live implementation you can inspect right now.
- [Is it safe to give an AI agent access to your ad account? A practical checklist](https://www.agentplanners.com/blog/ai-safety-checklist-ad-account-access): Ten concrete questions to ask before connecting any AI tool to a live ad account — approval gates, credential storage, magnitude limits, audit logs and more. Vendor-neutral, usable for evaluating any tool, including ours.
- [How to run one Google Ads goal across your entire MCC with an AI agent](https://www.agentplanners.com/blog/google-ads-mcc-fanout-with-ai-agent): Managing dozens of Google Ads sub-accounts under one manager account (MCC) means repeating the same audit or optimization by hand, per account. Here's how an AI agent fans one goal out across a whole MCC, with a dry-run preview per account.
- [DV360 reach forecasting and campaign planning with an AI agent](https://www.agentplanners.com/blog/dv360-reach-forecasting-and-campaign-planning): Before a DV360 line item ever goes live, reach forecasting answers the budget-vs-audience question. Here's how an AI agent runs that workflow end to end — plannable products, forecast simulation, targeting lookup.
- [How to automate Campaign Manager 360 (CM360) reporting and ad-server audits with an AI agent](https://www.agentplanners.com/blog/cm360-reporting-automation-and-ad-server-audits): CM360's role is cross-channel ad-server truth — but pulling and reconciling its reports by hand doesn't scale. Here's the concrete workflow for automating CM360 reporting and entity audits with an AI agent.
- [DeepSeek V4 Flash is available in Agent Planners: a 1M-context, ultra-low-cost model](https://www.agentplanners.com/blog/deepseek-v4-flash-in-agent-planners): DeepSeek V4 Flash pairs a 1-million-token context window with some of the lowest per-token pricing on the AI Gateway. Real current pricing, where it fits among Agent Planners' six agents, and how new models like it surface automatically.

## Key facts
- Approval model: reads run freely; every write waits for human approval (in-app or email magic-link). Optional per-task auto-approve for hands-off runs.
- Credits: usage is metered in credits (a fixed slice of real model + tool cost), billed per organization. Free tier includes 2,500 credits/month that reset; paid plans and one-time top-up packs add more.
- Agents: orchestrator + Analytics, Optimization, Creative, Research, Safety and Report specialists; each runs on a model you choose (GPT, Claude, Gemini, Qwen, DeepSeek and more) via one AI Gateway.
- Extensibility: connect your own tools via a custom MCP (Model Context Protocol) Streamable-HTTP server, or thousands of SaaS actions via Composio.
- Platforms: native OAuth integrations with Google Ads (incl. MCC), DV360, Meta Ads, TikTok Ads, Google Ad Manager, AdSense, AdMob, GA4, Search Console, BigQuery and Shopify, plus 250+ more apps via Composio and custom MCP servers.

## Frequently asked questions
- **Is my account safe?** Yes — security is our first priority. Every write pauses at an approval gate, every action lands in an operation / audit log, and you get email notifications for approvals and completions. Every integration, key and permission can be deleted and revoked at any time.
- **Will it change anything without my approval?** No. Reads are free; every mutation waits for a human — approve in-app, by magic-link email, or pre-approve a task when you explicitly want it hands-off. A single rejected step is skipped, not the whole run.
- **How do approvals actually work — in-app or by email?** Both. Each pending write shows its title, the agent's reasoning, the exact tool and arguments, and the task goal. Approve it in the Workspace, or click a one-time magic-link sent to an approver's email. Before a write runs, the Safety agent re-validates live account state, so a plan built on stale data is rejected rather than applied.
- **Which platforms does it support?** Natively, over OAuth or a pasted token: Google Ads (deep, pinned to API v22, including MCC), Display & Video 360, Campaign Manager 360, Google Ad Manager, AdSense, AdMob, Google Analytics 4, Search Console, BigQuery, Meta Ads, TikTok Ads and Shopify. See platform-by-platform use cases on the Platforms page. Plus 250+ more apps (Gmail, Outlook, Slack, HubSpot, Salesforce, Notion…) via Composio and your own MCP servers.
- **Does it support manager accounts (MCC) and multiple accounts at once?** Yes. Connect Google Ads with its MCC hierarchy and select many accounts in the context picker — the agent fans one goal across them. Cross-account writes always show a dry-run blast-radius preview first, then re-validate live state before applying.
- **Can I connect my own tools or MCP server?** Yes. Add a custom MCP (Model Context Protocol) server on the Integrations page — give it a name, a Streamable-HTTP URL and an optional token — and the agent auto-discovers and calls its tools. For pre-built SaaS actions (Slack, HubSpot, Salesforce and more) connect Composio instead.
- **Can I drive it from Claude, Codex, or my own scripts?** Yes — the opposite direction from custom MCP servers above: here, an external agent calls in to run tasks on your accounts. Agent Planners exposes a REST API and an MCP server, both authenticated with per-organization API keys. Point Claude Desktop or Claude Code at the MCP server, or call the REST API from Codex, a script or a CI job — either way it runs on the same orchestrator, with the same approval gates and credit metering as a task started in the Workspace.
- **Can I use my own models?** Yes. The orchestrator and each specialist agent run on whatever model you choose, switchable any time on the Agents panel through the built-in AI Gateway — GPT-5.5, Claude, Gemini, Qwen, DeepSeek and more. By default the orchestrator uses a quality-first planner and specialists use a fast, low-cost model.
- **Can I point it at my own model deployment?** Yes — Bring Your Own Model, included on any paid plan. Point every agent at your own OpenAI-compatible endpoint (Azure AI, vLLM, OpenRouter, self-hosted) and its LLM tokens are zero-rated — you pay your provider directly instead of platform credits. Tool, browser and sandbox calls still meter as usual, and saving runs a live test call first, so a dead endpoint never persists.
- **How do credits work?** Usage is metered in credits, billed per organization. A credit is a fixed slice of real model and tool cost: tasks spend credits on language-model tokens plus any external tools they call (web search, image/video generation, browser sessions, the Python sandbox). Cheaper models cost far fewer credits, so most of your burn depends on which models your agents use — a typical optimization task runs roughly 1,000–1,400 credits.
- **How much does it cost — and is there a free tier?** Every organization gets free monthly credits (2,500 on the free tier) with no credit card required to start. Paid plans raise the monthly allotment and one-time top-up packs add credits that stack on your balance. See the Billing page for current pricing and to upgrade or top up.
- **Do unused credits roll over?** Plan credits reset each billing period and don't roll over. One-time top-up packs stack on your balance and do not reset, so they're there until you use them.
- **What happens when I run out of credits?** Runs are blocked at zero credits until the next monthly reset, a plan upgrade, or a top-up pack — nothing is charged silently. You can watch your balance and usage (by day and by model) on the Billing page.
- **Can I schedule recurring tasks?** Yes. Turn any goal into a scheduled job on a cron — hourly, daily, weekly or a raw expression — in your timezone. Each fire regenerates a fresh plan against live data, so a recurring optimization never re-proposes yesterday's actions. You can set an approver email, enable auto-approve, or trigger a Run now any time.
- **Does it remember my targets and rules?** Yes. Each connected account carries durable memory — target CPA/ROAS, protected campaigns (e.g. never pause anything matching "brand*"), excluded geos, pacing and custom rules — that the agent reads on every run and you can edit on the Memory page. You can also capture your methods as reusable Skills.
- **Does it work for agencies and multiple clients?** Yes. Every workspace is an organization with isolated accounts, integrations, skills, assets, audit log and billing. Create as many orgs as you need, set per-member roles (admin / editor / member), and fan one goal out across an entire MCC.
- **How is my data handled?** OAuth credentials and tokens are encrypted at rest and isolated per organization, and are never returned to the browser. Reads and writes are scoped to the accounts you connect, every mutation is recorded in the audit log, and you can revoke any integration or key at any time. See the Privacy page for details.
- **What language does it speak?** Whatever you write in. Plans, reports and the agent's own memory all match your language — describe a goal in English, 中文, 日本語 or others and get the same plan and the same guardrails.
- **What do I need to get started?** No installation. Sign up, create your organization, connect an account on the Integrations page via OAuth, then write a goal in plain language in the Workspace. The orchestrator plans the steps and waits for your approval on anything that writes. The full guides live in the Documentation.

## Links
- [Home](https://www.agentplanners.com/)
- [Pricing](https://www.agentplanners.com/pricing)
- [Documentation](https://www.agentplanners.com/docs)
- [Platforms](https://www.agentplanners.com/platforms)
- [Guides & glossary](https://www.agentplanners.com/resources)
- [Comparisons](https://www.agentplanners.com/compare)
- [Alternatives](https://www.agentplanners.com/alternatives)
- [Blog](https://www.agentplanners.com/blog)
- [AI model pricing calculator](https://www.agentplanners.com/tools/ai-model-pricing)
- [AI model explorer](https://www.agentplanners.com/tools/model-explorer)
- [Full text for LLMs](https://www.agentplanners.com/llms-full.txt)
- [Sign up](https://www.agentplanners.com/sign-up)